ASU researchers tap AI to help people see more clearly

Yalin Wang, PhD, is shown at work in his office. The researcher in the School of Computing and Augmented Intelligence and his team have published a series of papers that outline their research. (Image credit: Nora Skrodenis/ASU)

Myopia is in the rise, particularly among children, and experts predict that by the year 2050, myopia will affect approximately half of the world’s population.

Researchers from Arizona State University maintain that a rise in what’s called near work — when individuals interact with close objects like phones and screens — is partially to blame.

For a number of individuals, the challenge to see faraway objects is a problem easily managed with glasses or contacts, but for others this develops into a far more serious condition called myopic maculopathy.

A team of researchers in the School of Computing and Augmented Intelligence at Arizona State University, is developing new diagnostic tools that use the power of artificial intelligence, or AI, to more effectively screen for this disease.

The research team has recently published the results of its work in the peer-reviewed research journal JAMA Ophthalmology.^1,2

Myopic maculopathy occurs when the part of the eye that helps us see straight ahead in sharp detail is damaged and stretched. With time, the shape of the eye becomes elongated — more like a football and less like a sphere. When this happens, vision is distorted.³

The condition is the leading cause of severe vision loss or blindness. Just a decade ago, myopic maculopathy led to visual impairment in 10 million individuals. Experts say that unless changes occur, more than 55 million people are predicted to have vision loss and approximately 18 million people worldwide will be blind due to the disease by 2050.⁴

Since myopic maculopathy is irreversible, experts are stressing the importance of early intervention. Early detection can lead to better outcomes, which is vitally important when children are involved. Ophthalmologists can prescribe special contact lenses or eye drops that slow the progression of the disease.¹

According to Yalin Wang, PhD, a Fulton Schools professor of computer science and engineering, innovations in technology can lead to important solutions.¹

“AI is ushering in a revolution that leverages global knowledge to improves diagnosis accuracy, especially in its earliest stage of the disease,” he said. “These advancements will reduce medical costs and improve the quality of life for entire societies.”

Seeing things in a new way

Amid the rise in myopia, the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society laid down a challenge last year. The group that seeks to drive innovation in biomedical research asked experts to improve computer-aided screening systems for retinal images.⁵

Moreover, ophthalmologists currently diagnose myopic maculopathy with optical coherence tomography scans that use reflected light to create pictures of the back of the eye. These scans are then often manually inspected by an ophthalmologist, a time-consuming process that can require specialized experience.¹

Wang, with the team at the Geometry Systems Laboratory, responded, and were among the winners of the MICCAI challenge.

During the first portion of the work, Wang and his team — which includes computer engineering doctoral student Wenhui Zhu as well as neurologist and Fulton Schools adjunct faculty member Oana Durmitrascu, MD, addressed the classification of myopic maculopathy.

Durmitrascu explained the disease has 5 classifications that describe its severity. Determining the correct level helps ophthalmologists to provide more tailored, effective solutions to the patient.¹

The researchers at Fulton Schools developed new AI algorithms called NN MobileNet. The sets of instructions that computer programs follow to do their work are developed to help software more effectively scan retinal images and predict the correct classification of the myopic maculopathy.

Next, the investigators trained their attention on efforts in the scientific community to use a type of AI called deep neural networks to predict the spherical equivalent in retinal scans. The spherical equivalent is an estimate of the eye’s refractive error that ophthalmologists and optometrists need when prescribing glasses or contacts. In deep neural networks, researchers task computers with analyzing huge sets of data and apply AI-powered algorithms to draw helpful conclusions.^1,2

Armed with a more accurate measure of the spherical equivalent, physicians can make more accurate treatment recommendations. Wang and the team again developed new algorithms that zeroed in on data relevance and quality. The resulting model of retinal image analysis achieved exceptional results while minimizing the amount of computing power needed.⁶

Finally, Wang collaborated with other winning teams from the MICCAI challenge on a third research paper that was published in JAMA Ophthalmology in September and outlined the results.⁷

Researchers from universities worldwide provided their challenge results to drive additional advancements and discoveries in the early and effective diagnosis of myopic maculopathy and improving health care outcomes for people across the globe.¹

A better vision for global health

According to Wang, a motivating force behind his work is to solve health disparities.

“People living in rural areas find it difficult to access sophisticated imaging devices and see physicians,” Wang explained. “Once AI-powered technology becomes available, it will significantly improve the quality of life in worldwide populations, including those who live in developing countries.”

According to Ross Maciejewski, director of the School of Computing and Augmented Intelligence, Wang’s work is an important example of the work being done by faculty members in the medical space.¹

“With both myopia and myopic maculopathy increasing, solutions are needed to prevent vision loss and help health care professionals provide the best treatment options for their patients,” Maciejewski concluded. “Yalin Wang’s innovative research is a principled use of artificial intelligence to address this dire medical issue.”

References

1. ASU researchers use AI to help people see more clearly. EurekAlert! Published October 2, 2024. Accessed October 7, 2024. https://www.eurekalert.org/news-releases/1060079

2. Qian B, Sheng B, Chen H, et al. A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms. JAMA Ophthalmol. Published online September 26, 2024. Accessed October 7, 2024. doi:10.1001/jamaophthalmol.2024.3707

3. S. Srakocic. Myopic Macular Degeneration: What You Should Know About Pathological Myopia. Healthline. Published May 2, 2022. Accessed October 7, 2024. https://www.healthline.com/health/eye-health/myopic-macular-degeneration#causes

4. Zhu X. Myopic Maculopathy: What Is It and How Is It Treated? Review of Myopia Management. Published June 4, 2020. Accessed October 7, 2024. https://reviewofmm.com/myopic-maculopathy-what-is-it-and-how-is-it-treated/

5. MICCAI. Miccai.org. Published 2024. Accessed October 7, 2024. https://miccai.org

6. Li H, Zhu W, Chen X, Wang Y. Prediction of Spherical Equivalent with Vanilla ResNet. Lecture notes in computer science. Published online January 1, 2024:66-74. doi:https://doi.org/10.1007/978-3-031-54857-4_6

7. Qian B, Sheng B, Chen H, et al. A Competition for the Diagnosis of Myopic Maculopathy by Artificial Intelligence Algorithms. JAMA Ophthalmol. Published online September 26, 2024. Accessed October 7, 2024. doi:10.1001/jamaophthalmol.2024.3707